No abstract

Physical, mechanical and dynamic properties of composites produced from coconut fibres using pure water sachet (LDPE) as matrix were evaluated in this study in order to assess its suitability for use as particleboards. The LDPE (waste water sachets) and coconut coir/fibre were collected, shredded and milled into pellets. Five compositions with coconut fibre loading 5, 10, 15, 20, and 25%, and corresponding LDPE of 95, 90, 85, 80 and 75%. A sixth sample with 100% LDPE was also produced as control. The LDPE samples were heated at 170°C for 30 minutes, and each melted solution was loaded with the corresponding coconut fibres and the mixture stirred and poured into a pre-designed metallic mould, pressed and cured in air for 24 hours. The results show that water absorption, swelling thickness and flaking concentration increased with, while the density decreased. The bending strength decreased with fibre loading, while the tensile strength, compressive strength and modulus of elasticity increased with increasing loading to a point before decreasing sharply. The results of dynamic mechanical analysis for the storage and loss modulus shows that as the temperature of the samples was increased these properties reduced except for the damping factor which increased. On the whole, the results showed that the sample with 15% coconut fibres loading and 85% LDPE exhibits more desirable properties compared with the others. These results imply that the composites produced from coconut fibres with LDPE as a matrix can be used as particleboards as well as in areas other areas of applications in the automobile industries. This will improve on savings in foreign exchange and mitigate environmental degradation as result of indiscriminate disposal of portable water sachets and coconut fibres.

Prediction of corrosion behavior of steel in acidic environments is an essential step towards optimizing the design of equipment in any industrial setting. An artificial neural network (ANN) may be used as a reliable modeling method for simulating and predicting the corrosion behaviour. The present study has been conducted to investigate the corrosion inhibition potentials of Eichhornia crassipes (water hyacinth) leaves extract for mild steel in acidic media and to establish an appropriate ANN model for predicting corrosion behavior of mild steel in H 2 SO 4 inhibited by Eichhornia crassipes. The experimental procedure employed weight loss method for corrosion rate measurements. Results have shown that Eichhornia crassipes is an effective inhibitor for corrosion inhibition of mild steel in acidic medium. A Levenberg-Marquardt (LM) ANN with single hidden layer having five neurons was employed to simulate the corrosion behaviour. The neural network was trained using the experimental corrosion database. Finally, validity of the proposed model was tested using standard statistical parameters. Results indicate that the trained ANN model is robust for predicting corrosion behaviour of mild steel in acidic media.

Artificial neural network assessment and modeling of job satisfaction of the Information and Communications Technology (ICT) Directorate workers of Federal University of Agriculture, Makurdi was investigated in this study. Modified Nordic Musculoskeletal Disorder (NMDQ) questionnaires which incorporated health, safety and environment factors were used. The questionnaire consisted of a series of objective questions with 'yes', 'no' and 'I don't know' responses and some were multiple choice questions. Parameters such as health, safety, environment and ergonomic factors were obtained from questionnaires for the modelling of workers efficiency and job satisfaction. The efficiency of workers was determined and normal probability curve for the 40 workers was plotted to identify the outliers. The artificial neural network (ANN) modeling method was employed to predict job satisfaction using health, safety, environment and ergonomic factors as input parameters while job satisfaction was the output. Series of network architectures were considered using different training algorithms. The scale conjugate gradient SCG 4 [3-3] 2 1 was adopted as the suitable network architecture for predicting job satisfaction. Result indicated that the predicted values of job satisfaction were in the range of 1.42 -2.00 as compared with the actual values of 1.50 -2.00 obtained from the questionnaires. Statistical indicators of normal error (E), used for validation of the model gave minimal errors and varied in the range of -0.48 -0.08. The plot of the normal probability curve also indicated the presence of outliers or inefficient workers. Whereas most of the workers were satisfied with the existing health, safety, environment (HSE) and ergonomics (E) programs at the work place, some (outliers) were not. The presence of outliers calls for improvement of ergonomic conditions at the ICT directorate.